本文採用紀錄輪廓特質的方法作為區域性影像擷取系統中的形狀特徵描述子。這個方法是從輪廓中取出n 個不連續點，紀錄參考點和其他n-1個點之間距離以及方位的關係。除了因旋轉輪廓而使的上述的紀錄資料改變之外，因水平或垂直翻轉輪廓所造成的改變也不容忽視。而對於具有旋轉或者翻轉關係的，將其視為相似的輪廓特質並群聚為k個群組，對各個群組給予符號，使輪廓的描述資料由原本的n個不連續點，轉為k個符號表示。對於作為質詢的輪廓，先計算出各個符號出現的次數再和資料庫中的圖片做比對，便能快速的找出相似、旋轉後相似或是翻轉後相似的圖片。
　　為了讓使用者能對不同型態的圖片做比對，本文提出在系統中加入具有選擇性的參數，讓使用者可以依照需求來決定是否需要使用到旋轉或翻轉的比對方法，使輸出的影像比對結果更為理想。

The shape context is used as the shape feature descriptor in a region-based image retrieval system in this thesis. The representation for a shape is a record of distances and positions between a reference point and other n-1 points of n discrete points detected from this shape. Similar representations after rotated or reflected are clustered together and each cluster is given a label. Then a shape description transforms from n discrete points into k labels. The calculation complexity and retrieval rate are improved by using labels. Rotation Invariance and reflection invariance join together make the retrieval precision increasing.
To retrieve images of different categories efficiently, system parameters to be used by users are proposed. Users can choose the match technology, whether rotation, reflection or not, to obtain ideal results.

[1] A. Ghosh and N. Petkov, “Robuatness of Shape Descriptors to Incomplete Contour Representations,” IEEE trans. Pattern Analysis and Machine Intelligence, vol. 27, pp. 1793－1804, 2005.

[2] A. Thayananthan, B. Stenger, “Shape Context and Chamfer Matching in Cluttered Scenes,” Proc. IEEE Comp. Soc. Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 127－133, 2003.

[3] B. Leibe and B. Schiele, “Analyzing Appearance and Contour Based Methods for Object Categorization,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 409 – 415, 2003.

[4] C. Faloutsos, R. Barber, M. Flickner, J. Hafner, W. Niblack, D. Petkovic and W. Equitz, “Efficient and Effective Querying by Image Content,” Journal of Intelligent Systems, pp. 231－262, 1994.

[5] C. T. Hsu, “Research of Multimedia Processing Laboratory,” (http://mp.cs.nthu.edu.tw/research.htm)

[6] D. Liu and T. Chen, “Soft Shape Context for Iterative Closest Point Registration,” International Conf. Image Processing, vol. 2, pp. 24－27, 2004.

[7] F. Jing, M. Li, H. J. Zhang, and B. Zhang, “Relevance Feedback in Region-Based Image Retrieval,” IEEE Trans. Circuits and Systems for Video Technology, vol. 14, pp. 672 – 681, 2004.

[8] F. Jing, M. Li, H. J. Zhang, and B. Zhang, “An Efficient and Effective Region-Based Image Retrieval Framework,” IEEE Trans. Image Processing, vol. 13, pp. 699 – 709, 2004.

[9] F. Mokhtarian and A. K. Mackworth, “A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, pp. 789－805, 1992.
[10] F. Jing, M. Li, H. J. Zhang, and B. Zhang, “Unsupervised Image Segmentation Using Local Homogeneity Analysis,” Proc. IEEE Int. Symp. Circuits and Systems, vol. 2, pp. 456 – 459, 2003.

[11] F. Mokhtarian and R. Suomela, “Robust Image Corner Detection Through Curvature Scale Space,” IEEE trans. Pattern Analysis and Machine Intelligence, vol. 20, pp. 1376－1381, 1998.

[12] G. Mori, S. Belongie and J. Malik, “Shape Contexts Enable Efficient Retrieval of Similar Shapes,” Proc. IEEE Comp. Soc. Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 723－730, 2001.

[13] G. Mori, S. Belongie and J. Malik, “Efficient Shape Matching Using Shape Contexts,” IEEE trans. Pattern Analysis and Machine Intelligence, vol. 27, pp. 1832－1837, 2005.

[14] G. Carneiro and A. D. Jepson, “Pruning Local Feature Correspondences Using Shape Context,” Proc. Int. Conf. Pattern Recognition, vol. 3, pp. 16－19, 2004.

[15] H. Zhang and J. Malik, “Learning A Discriminative Classifier Using Shape Context Distances,” Proc. IEEE Comp. Soc. Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 242－247, 2003.

[16] J. Huang, S. R. Kumar, M. Mitra, W.-J. Zhu, and R. Zabih, “Image Indexing Using Color Correlograms,”Proc. IEEE Comp. Soc. Conf. Computer Vision and Pattern Recognition, pp. 762－768, 1997.

[17] J. Z. Wang, J. Li, and G. Wiederhold, ”SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture Libraries,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, pp. 947 – 963, 2001.

[18] J. Li, J. Z. Wang, and G. Wiederhold, “IRM: Integrated Region Matching for Image Retrieval,” Proc. of the 8th ACM Int. Conf. on Multimedia, pp. 147 – 156, 2000.
[19] K. Vu, K. A. Hua, and W. Tavanapong, “Image Retrieval Based on Regions of Interest,” IEEE Trans. Knowledge and Data Engineering, vol. 15, pp. 1045 – 1049, 2003.

[20] M. Stricker and M. Orengo, “Similarity of Color Images,” Proc. SPIE Storage and Retrieval for Image and Video Databases III, vol. 2420, pp. 381 – 392, 1995..

[21] M. Yusuf and T. Haider, “Recognition of Handwritten Urdu Digits Using Shape Context,” Proc. Int. Multitopic Conference, pp. 569－572, 2004.

[22] R. Baeza-Yates and B. Ribeiro-Neto, Modern Information Retrieval. Reading, MA: Addison-Wesley, 1999

[23] S. Belongie and J. Malik, “Matching with Shape Contexts,” IEEE proc. Content-Based Access of Image and Video Libraries, pp. 20－26, 2000.

[24] S. Belongie, J. Malik and J. Puzicha, “Shape Matching and Object Recognition Using Shape Contexts,” IEEE trans. Pattern Analysis and Machine Intelligence, vol. 24, pp. 509－522, 2002.

[25] “The Math Works,” (http://www.mathworks.com/)

[26] W. C. Yen, “Image Retrieval by Using Shape Context,” Department of E.E. NCKU, Tainan, Taiwan, R.O.C., 2006.

[27] X. J. Qiu, Z. Q. Wang, S. H. Xia and J. T. Li, “Estimating Articulated Himan Pose from Video Using Shape Context,” Proc. IEEE Int. Symp. Signal Processing and Information Technology, pp. 583－588, 2005.

[28] Y. Deng, B. S. Manjunath, C. Kenney, M.S. Moore and H. Shin, “An Efficient Color Representation for Image Retrieval,” IEEE Trans. Image Processing, vol. 10, pp. 140－147, 2001.